Back to vendors
I

Imbue

Also known as: Imbue Sculptor, Generally Intelligent

Visit site
Entry priceFree and open source (MIT); uses your own Claude planFull pricing detail

Desktop app from Imbue, an AI research lab working on verifying the correctness of AI generated code, for running parallel coding agents, each in its own isolated git worktree, with every change reviewed by the developer before it is merged.

Imbue is a San Francisco AI research lab, formerly known as Generally Intelligent and founded in 2018, that builds tools to make AI coding reliable, collaborative, and accessible. Led by chief executive Kanjun Qiu, it has raised roughly two hundred thirty two million dollars from investors including NVIDIA, Eric Schmidt, Cruise founder Kyle Vogt, and Notion co founder Simon Last, and it operates a ten thousand graphics processor research cluster. Its research mission is to improve the ability to verify the correctness of code generated by large language models, so people can trust the software they build.

Imbue's first product is Sculptor, a desktop application for macOS and Linux for running parallel coding agents. Each agent works in its own isolated git worktree with its own branch and terminal, with a Docker or remote container backend available as an experimental option, and five or more agents can run at once from one workspace. Sculptor offers Claude models out of the box on the developer's own Claude plan, and its support for the Pi agent harness lets developers choose any provider or run any terminal based agent. It is designed to let a developer kick off a refactor with one agent while another builds a feature and a third checks a hunch.

Control sits at the center. Each agent's changes reach the codebase only when the developer reviews the diff and merges, Pairing Mode syncs an agent's work into the local editor so changes can be tested and reviewed, and Sculptor opens GitHub pull requests and tracks their status. A built in library of workflow skills runs as full agents, including a fix bug skill that writes failing tests before fixing, and a CI Babysitter dispatches agents to fix failing pipelines.

Sculptor runs fully locally, with granular control over what data returns to Imbue and no training on a user's code by default. It is free and open source under the MIT license, and the customer pays the model provider directly. As a focused developer tool, not a general business agent platform, it does not offer enterprise security certifications or business system integrations. Its strength is orchestrating coding agents while keeping every change under the developer's review.

Vendor details

Canonical URL

https://imbue.com

Category

Agent builder

Subcategory

Desktop harness for running and verifying parallel coding agents in isolated containers

Funding status

Independent research lab. Founded 2018 as Generally Intelligent by Kanjun Qiu and Josh Albrecht, renamed Imbue, based in San Francisco. Reported to have raised roughly $212M to $232M from investors including NVIDIA, Eric Schmidt, Kyle Vogt and Simon Last, operating a large research GPU cluster. Sculptor is its first product, in beta and free during beta, with the customer supplying their own Anthropic API key or Claude Pro or Max subscription; long-term pricing is not published. Public repository last active May 2026 at v0.30.

Company status

independent

Use cases & customers

Primary use cases

Running several coding agents in parallel, each in an isolated container, without dependency collisions or risk to the local machineSyncing any agent's work into the local repository and IDE to test it before mergingEnforcing plain-English rules on agent output through instruction audits, and catching tests that falsely report passingUsing Claude Code or Codex with your own API key or Claude subscription, with no vendor between you and the modelKeeping source code entirely on the developer's own machine, with granular control over what telemetry returns to the vendor

Deployment options

local

Integrations

Sculptor integrates with the developer's own toolchain rather than business systems: local git repositories, with each agent in its own worktree and branch and Pairing Mode syncing an agent's work into the local repository, the developer's own IDE and dev environment, an experimental Docker or remote container backend, devcontainer configuration with port forwarding, and linters including pylint, ruff and pyre integrated into verification. Claude Code runs on the customer's own Claude plan, and the Pi agent harness opens any provider and any terminal-based agent. Customers can build their own Sculptor plugins in JavaScript or TypeScript and swap the agent harness entirely, and Sculptor opens GitHub pull requests and tracks their status. No business system connectivity exists and none is intended; tool calling within a task belongs to the underlying coding agents.

In practice

A developer wants to explore three approaches at once. In Sculptor they run three agents in parallel, each in its own isolated worktree with its own branch, terminal and diff view, on a refactor, a new feature and a bug fix, then move between them with nothing bleeding between.

An engineer wants every agent's changes checked before they land. Each Sculptor agent works on its own branch with its own diff view, and its changes reach the codebase only when the developer reviews the diff and merges.

A failing CI run blocks a release. Sculptor's CI Babysitter dispatches an agent to fix the pipeline, and the fix reaches the codebase only after the developer reviews the diff and merges.

Agentic Index coverage score

9.0 / 14 capabilities · 64%

Integrations & Tool Calling Partial

Sculptor works with local git repositories, keeping files and git state in sync between an agent's container and the developer's local repository through Pairing Mode, and works alongside the developer's own IDE and environment. Docker gives each agent a container with a full copy of the repository, and a later release added devcontainer port forwarding.

Linters including pylint, ruff and pyre run as part of the verification checks. Supported coding agents are Claude Code and Codex, and Imbue invites requests for others. There is no connection to business systems such as CRM, ticketing, messaging or data warehouses, and tool calls within a task are made by the underlying coding agents, not by Sculptor.

Sourceimbue.com sculptor product page and Sculptor announcement, public release notesread 2026-08-31

Workflow Orchestration Full

Five or more coding agents can run in parallel, each in an isolated worktree with its own branch, terminal and diff view, all visible and mergeable from one workspace, and skills run as full agents that can spawn parallel subagents. A developer reviews and merges each agent's changes, and Sculptor opens GitHub pull requests and tracks their status.

Sourceimbue.com/product/sculptor and github.com/imbue-ai/sculptor READMEread 2026-09-29

Knowledge Grounding & RAG Partial

Each coding agent runs in a container with a full copy of the developer's repository, so it works from the whole codebase, not retrieved fragments, and devcontainer support supplies the project's environment configuration. Instruction audit rules that the developer writes in plain English persist as policy applied to agent work. Sculptor keeps no index, ingestion pipeline, document or wiki source, curated knowledge object or retrieval setup beyond the repository, which the customer maintains through git and which is copied into the container.

Sourceimbue.com sculptor product page and Sculptor announcementread 2026-08-31

Human Oversight & Guardrails Partial

Each Sculptor agent works in its own worktree and branch and pushes to a local git remote, and its changes reach the codebase only when the developer reviews the diff and merges, which Imbue calls full review before merge. The merge is the customer's own gate, not an approval step inside the agent's run. Instruction audits, plain English rules checked against an agent's work, were listed as coming next in the Sculptor announcement but do not appear on the current product page or README.

Sourceimbue.com/product/sculptor, Sculptor announcement and github.com/imbue-ai/sculptor READMEread 2026-09-29

Security, Identity & Governance Partial

Each coding agent runs in its own Docker container, so it can install packages and run code without risking the developer's machine, unlike git worktrees, which share the local environment. Sculptor runs fully locally, with data sharing levels that control what goes back to Imbue.

The Essential only level shares just error logs and basic usage, which Imbue calls the safe choice for work code, and code is not used for training by default. There is no security certification, trust center, single sign on, role based access control or team audit capability, since the product is a desktop app for a single developer, in beta.

Sourceimbue.com sculptor product page and Sculptor announcementread 2026-08-31

Observability & Auditability Partial

Sculptor shows a diff for each agent's changes, which is review of output, not a record of each step the agent took. Pairing Mode brings an agent's work from its container into the local repository with files and git state in sync, so changes can be inspected in the developer's own editor and diff tools, and merges show conflicts to resolve.

At launch, every agent session was saved with its plans, chats, tool calls and code changes intact and could be resumed and forked from any point, but the current product page and README no longer describe this. Suggestions, which flagged misleading agent behavior such as tests that falsely report passing, no longer appears either. There is no analytics across sessions, fleet reporting or organizational dashboard.

Sourceimbue.com/product/sculptor and github.com/imbue-ai/sculptor READMEread 2026-10-06

Memory & State Persistence Not documented

Sculptor has no memory between sessions. Neither the product page nor the README describes saving, resuming or forking a session. The launch announcement said every agent session was saved with its plans, chats, tool calls and code changes and could be resumed or forked from any point, but that no longer appears. Agents do not learn from corrections, carry conclusions between separate sessions or update their own instructions from experience, and they are kept apart from one another on purpose.

Sourcegithub.com/imbue-ai/sculptor README and imbue.com/product/sculptorread 2026-10-06

Deployment & Data Residency Full

Sculptor runs on the customer's own computer, not Imbue's servers. Data never leaves the machine, Imbue does not store repositories or train on code, and Sculptor is free, local and open source under the MIT license. Each agent works in an isolated git worktree with its own branch and terminal, and a Docker or remote container backend is experimental. It runs on macOS on Apple Silicon and on Linux, including ARM64.

Sourceimbue.com/product/sculptor and github.com/imbue-ai/sculptor READMEread 2026-09-29

Prebuilt Agents, Templates & Packs Full

Sculptor ships a library of workflow skills that run as full agents with their own tools. They cover spec writing, mock generation and a fix bug skill that runs a reproduction interview, writes failing tests and then makes them pass, with experimental skills listed separately and a CI Babysitter that fixes failing pipelines. The set is small and each skill is named.

Sourcegithub.com/imbue-ai/sculptor README and imbue.com/product/sculptorread 2026-09-29

Triggers & Channel Coverage Full

The CI Babysitter dispatches agents automatically to fix failing pipelines, so a CI failure starts work on its own, and Sculptor opens GitHub pull requests and tracks their status. Otherwise a developer launches agents on demand from the desktop app on macOS or Linux. The CI Babysitter rests on one line in the product page FAQ and is not in the README's feature summary.

Sourceimbue.com/product/sculptor and github.com/imbue-ai/sculptor READMEread 2026-09-29

Model Flexibility & Routing Full

Sculptor offers Claude models out of the box (Opus 4.8, 4.7 and 4.6, Sonnet 4.6, Haiku 4.5) on the customer's own Claude plan. It also supports the Pi agent harness, through which the customer can choose any provider or switch models mid session, and it can run any terminal based agent, so the choice spans model makers. The product page FAQ still calls Pi support experimental, and Codex is no longer listed.

Sourceimbue.com/product/sculptor and github.com/imbue-ai/sculptor READMEread 2026-09-29

APIs, SDKs & MCP Extensibility Full

Customers can build their own Sculptor plugins in JavaScript or TypeScript and swap the agent harness entirely. Sculptor supports the Pi harness alongside Claude Code and can run and manage any terminal based agent. It is open source under the MIT license, with a public repository and documentation. The plugin interface is described on the product page, but no plugin reference has been recorded.

Sourceimbue.com/product/sculptor and github.com/imbue-ai/sculptor READMEread 2026-09-29

Testing, Debugging & Optimization Partial

The Sculptor announcement listed Suggestions as a beta that points out fixes to agent code, and listed instruction audits and flagging misleading behavior, such as tests that pass without real tests, as coming next, so those were roadmap features.

The current product page and README describe diff review for each agent, a fix bug skill that writes failing tests before fixing, and a CI Babysitter, and mention neither Suggestions nor audits. Tests the agent writes and runs are part of its method, not a harness scoring its output. Imbue's separate open source tool for catching agent mistakes is another product.

Sourceimbue.com Sculptor announcement, imbue.com/product/sculptor and github.com/imbue-ai/sculptor READMEread 2026-09-29

Browser & Computer Use Not documented

Coding agents run code, install dependencies and run terminals and test suites inside isolated Docker containers, which is code execution, not operation of software without a programmatic interface. Devcontainer port forwarding lets a developer view an app running inside a container from their own browser, so the person, not the agent, looks at the output. All agent actions reach the filesystem, git, package managers and linters programmatically inside the container. No agent controls a browser, navigates, fills forms, interacts with a screen or automates a desktop.

Sourceimbue.com sculptor product page and Sculptor announcement, public release notesread 2026-08-31

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Pricing

Free and open source (MIT); uses your own Claude plan

Agentic Index verified 2026-09-29

Alternatives to Imbue

The closest documented capability profiles to Imbue among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Bika.ai10.0 / 14Adds documented Memory & State Persistence
  • Celigo10.5 / 14Fuller documented coverage on Integrations & Tool Calling and Security, Identity & Governance
  • Jet Admin9.5 / 14Adds documented Memory & State Persistence
  • Altilia10.5 / 14Fuller documented coverage on Knowledge Grounding & RAG and Human Oversight & Guardrails
  • Haptik10.5 / 14Fuller documented coverage on Integrations & Tool Calling and Knowledge Grounding & RAG
  • MoBagel6.5 / 14A lighter documented profile than Imbue

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Head to head

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.